Motion-Based Handwriting Recognition and Word Reconstruction

Abstract

In this project, we leverage a trained single-letter classifier to predict the written word from a continuously written word sequence, by designing a word reconstruction pipeline consisting of a dynamic-programming algorithm and an auto-correction model. We conduct experiments to optimize models in this pipeline, then employ domain adaptation to explore using this pipeline on unseen data distributions.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Kinect Sensor Based Gesture Recognition for Surveillance Application
• End-to-End Multi-speaker Speech Recognition with Transformer
• Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Network
• Motion-Based Handwriting Recognition
• End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection